Transform Fragmented Data into Connected Semantic Layer
Intugle’s GenAI-powered open-source Python library builds an intelligent semantic layer over your existing data systems. At its core, it discovers meaningful links and relationships across data assets — enriching them with profiles, classifications, and business glossaries. With this connected knowledge layer, you can enable semantic search and auto-generate queries to create unified data products, making data integration and exploration faster, more accurate, and far less manual.
- Data Engineers & Architects often spend weeks manually profiling, classifying, and stitching together fragmented data assets. With Intugle, they can automate this process end-to-end, uncovering meaningful links and relationships to instantly generate a connected semantic layer.
- Data Analysts & Scientists spend endless hours on data readiness and preparation before they can even start the real analysis. Intugle accelerates this by providing contextual intelligence, automatically generating SQL and reusable data products enriched with relationships and business meaning.
- Business Analysts & Decision Makers are slowed down by constant dependence on technical teams for answers. Intugle removes this bottleneck by enabling natural language queries and semantic search, giving them trusted insights on demand.
- Semantic Intelligence: Transform raw, fragmented datasets into an intelligent semantic graph that captures entities, relationships, and context — the foundation for connected intelligence.
- Business Glossary & Semantic Search: Auto-generate a business glossary and enable search that understands meaning, not just keywords — making data more accessible across technical and business users.
- Smart SQL & Data Products: Instantly generate SQL and reusable data products enriched with context, eliminating manual pipelines and accelerating data-to-insight.
For Windows and Linux, you can follow these steps. For macOS, please see the additional steps in the macOS section below.
Before installing, it is recommended to create a virtual environment:
python -m venv .venv
source .venv/bin/activateThen, install the package:
pip install intugleFor macOS users, you may need to install the libomp library:
brew install libompIf you installed Python using the official installer from python.org, you may also need to install SSL certificates by running the following command in your terminal. Please replace 3.XX with your specific Python version. This step is not necessary if you installed Python using Homebrew.
/Applications/Python\ 3.XX/Install\ Certificates.commandBefore running the project, you need to configure a LLM. This is used for tasks like generating business glossaries and predicting links between tables.
You can configure the LLM by setting the following environment variables:
LLM_PROVIDER: The LLM provider and model to use (e.g.,openai:gpt-3.5-turbo) following LangChain's conventionsAPI_KEY: Your API key for the LLM provider. The exact name of the variable may vary from provider to provider.
Here's an example of how to set these variables in your environment:
export LLM_PROVIDER="openai:gpt-3.5-turbo"
export OPENAI_API_KEY="your-openai-api-key"For a detailed, hands-on introduction to the project, please see our quickstart notebooks:
quickstart_healthcare.ipynb: This notebook will walk you through the entire process of building a semantic layer using a healthcare dataset.
quickstart_tech_company.ipynb
These datasets will take you through the following steps:
- Building a Knowledge Base: Use the
KnowledgeBuilderto automatically profile your data, generate a business glossary, and predict links between tables. - Accessing Enriched Metadata: Learn how to access the profiling results and business glossary for each dataset.
- Visualizing Relationships: Visualize the predicted links between your tables.
- Generating Data Products: Use the semantic layer to generate data products and retrieve data.
- Searching the Knowledge Base: Use semantic search to find relevant columns in your datasets using natural language.
The core workflow of the project involves using the KnowledgeBuilder to build a semantic layer, and then using the DataProductBuilder to generate data products from that layer.
from intugle import KnowledgeBuilder, DataProductBuilder
# Define your datasets
datasets = {
"allergies": {"path": "path/to/allergies.csv", "type": "csv"},
"patients": {"path": "path/to/patients.csv", "type": "csv"},
"claims": {"path": "path/to/claims.csv", "type": "csv"},
# ... add other datasets
}
# Build the knowledge base
kb = KnowledgeBuilder(datasets, domain="Healthcare")
kb.build()
# Create a DataProductBuilder
dp_builder = DataProductBuilder()
# Define an ETL model
etl = {
"name": "top_patients_by_claim_count",
"fields": [
{
"id": "patients.first",
"name": "first_name",
},
{
"id": "patients.last",
"name": "last_name",
},
{
"id": "claims.id",
"name": "number_of_claims",
"category": "measure",
"measure_func": "count"
}
],
"filter": {
"sort_by": [
{
"id": "claims.id",
"alias": "number_of_claims",
"direction": "desc"
}
],
"limit": 10
}
}
# Generate the data product
data_product = dp_builder.build(etl)
# View the data product as a DataFrame
print(data_product.to_df())For detailed code examples and a complete walkthrough, please see the quickstart notebooks under the notebooks directory.
The semantic search feature allows you to search for columns in your datasets using natural language. It is built on top of the Qdrant vector database.
To use the semantic search feature, you need to have a running Qdrant instance. You can start one using the following Docker command:
docker run -p 6333:6333 -p 6334:6334 \
-v qdrant_storage:/qdrant/storage:z \
--name qdrant qdrant/qdrantYou also need to configure the Qdrant URL and API key (if using authorization) in your environment variables:
export QDRANT_URL="http://localhost:6333"
export QDRANT_API_KEY="your-qdrant-api-key" # if authorization is usedCurrently, the semantic search feature only supports OpenAI embedding models. Therefore, you need to have an OpenAI API key set up in your environment. The default model is text-embedding-ada-002. You can change the embedding model by setting the EMBEDDING_MODEL_NAME environment variable.
For OpenAI models:
export OPENAI_API_KEY="your-openai-api-key"
export EMBEDDING_MODEL_NAME="openai:ada"For Azure OpenAI models:
export AZURE_OPENAI_API_KEY="your-azure-openai-api-key"
export AZURE_OPENAI_ENDPOINT="your-azure-openai-endpoint"
export OPENAI_API_VERSION="your-openai-api-version"
export EMBEDDING_MODEL_NAME="azure_openai:ada"Once you have built the knowledge base, you can use the search method to perform a semantic search. The search function returns a pandas DataFrame containing the search results, including the column's profiling metrics, category, table name, and table glossary.
from intugle import KnowledgeBuilder
# Define your datasets
datasets = {
"allergies": {"path": "path/to/allergies.csv", "type": "csv"},
"patients": {"path": "path/to/patients.csv", "type": "csv"},
"claims": {"path": "path/to/claims.csv", "type": "csv"},
# ... add other datasets
}
# Build the knowledge base
kb = KnowledgeBuilder(datasets, domain="Healthcare")
kb.build()
# Perform a semantic search
search_results = kb.search("reason for hospital visit")
# View the search results
print(search_results)For detailed code examples and a complete walkthrough, please see the quickstart notebooks under the notebooks directory.
Join our community to ask questions, share your projects, and connect with other users.
Contributions are welcome! Please see the CONTRIBUTING.md file for guidelines.
This project is licensed under the Apache License, Version 2.0. See the LICENSE file for details.